© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 131038
    Prev
    Next
    INDEX
    Explanations

    programming-related keywords and identifiers in a structured context

    oai_token-act-pair · gpt-4o-mini
    Triggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
     pragma
    -0.06
    ugi
    -0.06
    eshire
    -0.06
    asco
    -0.06
    ringe
    -0.06
    armor
    -0.06
    plets
    -0.06
    éra
    -0.06
    GIT
    -0.06
    ecast
    -0.05
    POSITIVE LOGITS
    verte
    0.06
     Cul
    0.06
    inae
    0.06
    .intellij
    0.06
     pon
    0.06
     VÅ¡ech
    0.06
    ulfilled
    0.06
     arsch
    0.06
    ìĿ´íĦ°
    0.06
    .dispatchEvent
    0.06
    Activations Density 1.165%

    No Known Activations